Ptacek argues LLMs belong in editing, not drafting
Thomas Ptacek articulates a contrarian stance on LLM integration into writing workflows: treat them as editorial tools rather than content generators. His core principle forbids adopting any phrasing an LLM suggests, positioning the technology as a fact-checking and grammar layer rather than a creative partner. This reflects a broader tension in the field between automation and authorial control, where practitioners are establishing guardrails to preserve voice and accountability while capturing efficiency gains. The approach signals how experienced writers are operationalizing LLMs within bounded, defensive frameworks.
Modelwire context
Skeptical readPtacek's rule (reject all LLM suggestions verbatim) is stricter than most 'responsible AI use' guidance, which typically allows selective adoption. The unstated assumption is that LLM phrasing is categorically inferior or dangerous to voice, but the piece doesn't test whether this holds for low-stakes editorial tasks like grammar or fact-flagging.
This is largely disconnected from recent activity in the space. Most LLM adoption coverage focuses on capability benchmarks, cost-per-token, or organizational rollout (funding rounds, hiring). Ptacek's piece belongs to a smaller, quieter conversation about writer autonomy and tool boundaries that hasn't yet surfaced in major coverage. We haven't tracked comparable first-person accounts from other experienced practitioners establishing similar guardrails, so this reads as an individual stance rather than an emerging pattern.
If other established writers (journalists, novelists, technical authors with public platforms) publish similar defensive frameworks in the next 6 months, that signals a real cohort forming around bounded LLM use. If adoption instead accelerates among the same group without public pushback, Ptacek's stance remains idiosyncratic.
This analysis is generated by Modelwire’s editorial layer from our archive and the summary above. It is not a substitute for the original reporting. How we write it.
MentionsThomas Ptacek · Simon Willison · LLM
Modelwire Editorial
This synthesis and analysis was prepared by the Modelwire editorial team. We use advanced language models to read, ground, and connect the day’s most significant AI developments, providing original strategic context that helps practitioners and leaders stay ahead of the frontier.
Modelwire summarizes, we don’t republish. Simon Willison originally reported this story as “How To Write With An LLM”. The full content lives on simonwillison.net. If you’re a publisher and want a different summarization policy for your work, see our takedown page.